Classify files

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses the cost model (one very cheap request per file), that confidence is calibrated, that files are read and returned grouped, and that label descriptions improve accuracy. It does not state that the operation is read-only/non-destructive nor mention rate limits or failure behavior for unreadable files.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded: purpose and cost appear in the first sentence, return shape in the second, use cases third, accuracy tip last. Every sentence earns its place, though the parenthetical cost note interrupts the main clause slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an eleven-parameter tool with no annotations and no output schema, the description covers purpose, cost, output grouping, and the key accuracy lever. Minor gaps: it only mentions the 'grouped' shape although format supports table/json, and it says nothing about dry_run or include/exclude interplay.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the eleven parameters are already well documented, including the colon-description convention for labels. The description reinforces that convention but adds no new syntax, defaults, or constraints beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (classify every file into your labels) plus the mechanism (decision model) and the return shape (files grouped by label). It is clear enough to act on, but it never differentiates itself from the sibling decide_files, which by name sounds closely related.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Concrete when-to-use guidance is given: triage of tests/configs/dead code, sorting documents by topic, flagging files about X. It lacks any exclusions or an explicit pointer to decide_files versus locate_in_files, so the agent must infer the boundary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.